TTS/vc/layers/freevc/mel_processing.py

import logging

import torch
import torch.utils.data
from librosa.filters import mel as librosa_mel_fn

from TTS.utils.audio.torch_transforms import amp_to_db

logger = logging.getLogger(__name__)

MAX_WAV_VALUE = 32768.0

mel_basis = {}
hann_window = {}


def mel_spectrogram_torch(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False):
    if torch.min(y) < -1.0:
        logger.info("Min value is: %.3f", torch.min(y))
    if torch.max(y) > 1.0:
        logger.info("Max value is: %.3f", torch.max(y))

    global mel_basis, hann_window
    dtype_device = str(y.dtype) + "_" + str(y.device)
    fmax_dtype_device = str(fmax) + "_" + dtype_device
    wnsize_dtype_device = str(win_size) + "_" + dtype_device
    if fmax_dtype_device not in mel_basis:
        mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax)
        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(dtype=y.dtype, device=y.device)
    if wnsize_dtype_device not in hann_window:
        hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(dtype=y.dtype, device=y.device)

    y = torch.nn.functional.pad(
        y.unsqueeze(1), (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)), mode="reflect"
    )
    y = y.squeeze(1)

    spec = torch.view_as_real(
        torch.stft(
            y,
            n_fft,
            hop_length=hop_size,
            win_length=win_size,
            window=hann_window[wnsize_dtype_device],
            center=center,
            pad_mode="reflect",
            normalized=False,
            onesided=True,
            return_complex=True,
        )
    )

    spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)

    spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
    spec = amp_to_db(spec)

    return spec